INDEX

Explanations

references to specific art pieces or designs

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.scalablytyped

-0.19

amiento

-0.15

 Brick

-0.15

éĻ¶

-0.15

.lex

-0.15

 Vinyl

-0.14

tep

-0.14

 concrete

-0.14

 brick

-0.14

vir

-0.14

POSITIVE LOGITS

orm

0.20

 chased

0.20

 punch

0.18

askell

0.17

Orm

0.17

 Punch

0.16

 famille

0.16

Roc

0.16

ORM

0.16

 presentation

0.16

Activations Density 0.036%

references to specific art pieces or designs

No Comments

No Known Activations